mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 30 Sep 2025

612 papers

  1. CustomIR: Unsupervised Fine-Tuning of Dense Embeddings for Known Document CorporaRetrieval-augmented generation → Generation and context integration
  2. Catalog-Native LLM: Speaking Item-ID Dialect with Less Entanglement for RecommendationLLM reasoning → LLM reasoning for recommendation
  3. MADS: Multi-Agent Dialogue Simulation for Diverse Persuasion Data GenerationLLM agents and tool use → Social simulation and multi-agent debate
  4. Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  5. F-scheduler: illuminating the free-lunch design space for fast sampling of diffusion modelsDiffusion models → Diffusion foundations and sampling
  6. From Trace to Line: LLM Agent for Real-World OSS Vulnerability LocalizationLLM agents and tool use → Agent threats, guardrails and governance
  7. Learning to Route: A Rule-Driven Agent Framework for Hybrid-Source Retrieval-Augmented GenerationRetrieval-augmented generation → Agentic RAG, agents and memory +1
  8. CWM: An Open-Weights LLM for Research on Code Generation with World ModelsWorld models → World models for language agents
  9. On The Fragility of Benchmark Contamination Detection in Reasoning ModelsLLM reasoning → Reasoning benchmarks and evaluation
  10. Secure and Robust Watermarking for AI-generated Images: A Comprehensive SurveyLLM safety and security → Watermarking generated content and models
  11. Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM SystemsLLM reasoning → Reasoning benchmarks and evaluation
  12. LLM-Based Multi-Agent Blackboard System for Information Discovery in Data ScienceLLM agents and tool use → Web, search, and research agents
  13. TUMIX: Multi-Agent Test-Time Scaling with Tool-Use MixtureLLM reasoning → Reasoning for agents, planning and code +1
  14. DiSA-IQL: Offline Reinforcement Learning for Robust Soft Robot Control under Distribution ShiftsOffline RL and imitation learning from data → Offline RL algorithms
  15. Hierarchical Reasoning Models: Perspectives and MisconceptionsLLM reasoning → Reasoning benchmarks and evaluation
  16. Flow Autoencoders are Effective Protein TokenizersDiffusion models → Flow matching, time series and science
  17. Learning Human Reaching Optimality Principles from Minimal Observation Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning +1
  18. Reasoning-Aware Prompt Orchestration: A Foundation Model for Multi-Agent Language Model CoordinationLLM reasoning → Reasoning for agents, planning and code +1
  19. DecepChain: Inducing Deceptive Reasoning in Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  20. Post-Training Quantization for Audio Diffusion TransformersDiffusion models → Audio, speech and music
  21. CORTEX: Collaborative LLM Agents for High-Stakes Alert TriageLLM agents and tool use → Agent threats, guardrails and governance
  22. Free Draft-and-Verification: Toward Lossless Parallel Decoding for Diffusion Large Language ModelsEfficient LLM inference and serving → Diffusion LLM and MoE inference
  23. MOLM: Mixture of LoRA MarkersLLM safety and security → Watermarking generated content and models
  24. Judging with Confidence: Calibrating Autoraters to Preference DistributionsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  25. Retrieval-Augmented Generation for Electrocardiogram-Language ModelsRetrieval-augmented generation → Medical and biomedical RAG
  26. A Hierarchical Agentic Framework for Autonomous Drone-Based Visual InspectionLLM agents and tool use → Multimodal and embodied agents
  27. TASER: Translation Assessment via Systematic Evaluation and ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  28. Can AI agents understand spoken conversations about data visualizations in online meetings?LLM agents and tool use → Multimodal and embodied agents
  29. Debunk the Myth of SFT GeneralizationDeep reinforcement learning methods → RL training of language and agent models
  30. The Pitfalls of KV Cache CompressionEfficient LLM inference and serving → KV cache optimization
  31. AgentFlux: Decoupled Fine-Tuning & Inference for On-Device Agentic SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  32. Thoughtbubbles: an Unsupervised Method for Parallel Thinking in Latent SpaceLLM reasoning → Test-time compute and efficient thinking
  33. Directed-MAML: Meta Reinforcement Learning Algorithm with Task-directed ApproximationDeep reinforcement learning methods → Deep RL algorithms and representations
  34. FlowMoE: A Scalable Pipeline Scheduling Framework for Distributed Mixture-of-Experts TrainingMixture-of-experts → Efficient MoE training and inference systems
  35. GRPO-λ: Credit Assignment improves LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  36. Thinkquel: A Model Dedicated to Text-to-dbt Using Synthetic Data and a Span-Aware ObjectiveLLM reasoning → Knowledge- and tool-augmented reasoning +1
  37. Object-Centric Case-Based Reasoning via ArgumentationLLM reasoning → Multimodal reasoning
  38. PrefDisco: Benchmarking Proactive Personalized ReasoningLLM reasoning → Reinforcement learning for reasoning
  39. Drones that Think on their Feet: Sudden Landing Decisions with Embodied AILLM reasoning → Spatial and embodied reasoning
  40. TAMA: Tool-Augmented Multimodal Agent for Procedural Activity UnderstandingLLM agents and tool use → Multimodal and embodied agents
  41. RoboPilot: Generalizable Dynamic Robotic Manipulation with Dual-thinking ModesLLM reasoning → Spatial and embodied reasoning
  42. Which Rewards Matter? Reward Selection for Reinforcement Learning under Limited FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  43. Direct Token Optimization: A Self-contained Approach to Large Language Model UnlearningLLM safety and security → Machine unlearning
  44. Judging by Appearances? Auditing and Intervening Vision-Language Models for Bail PredictionMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  45. Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A SurveyLLM reasoning → Reasoning for agents, planning and code +1
  46. Stitch: Training-Free Position Control in Multimodal Diffusion TransformersDiffusion models → Image generation, text-to-image and editing
  47. MLA: A Multisensory Language-Action Model for Multimodal Understanding and Forecasting in Robotic ManipulationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  48. Query-Kontext: An Unified Multimodal Model for Image Generation and EditingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  49. OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene InteractionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  50. Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning ModelsLLM reasoning → Reinforcement learning for reasoning
  51. TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal DistanceDeep reinforcement learning methods → RL for robot locomotion and manipulation
  52. Recursive Self-Aggregation Unlocks Deep Thinking in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  53. Fine-tuning Behavioral Cloning Policies with Preference-Based Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms +1
  54. MENLO: From Preferences to Proficiency -- Evaluating and Modeling Native-like Quality Across 47 LanguagesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  55. Clarification as Supervision: Reinforcement Learning for Vision-Language InterfacesLLM reasoning → Multimodal reasoning +1
  56. Fairness Testing in Retrieval-Augmented Generation: How Small Perturbations Reveal Bias in Small Language ModelsRetrieval-augmented generation → RAG robustness and adaptive retrieval +1
  57. Linking Process to Outcome: Conditional Reward Modeling for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  58. Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research BenchmarkLLM reasoning → Spatial and embodied reasoning
  59. Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function CallingLLM agents and tool use → Tool learning and function calling
  60. Towards Verified Code Reasoning by LLMsLLM reasoning → Reasoning for agents, planning and code +1
  61. Ferret-UI Lite: Lessons from Building Small On-Device GUI AgentsLLM agents and tool use → GUI and mobile agents
  62. HilbertA: Hilbert Attention for Image Generation with Diffusion ModelsDiffusion models → Video generation
  63. OceanGym: A Benchmark Environment for Underwater Embodied AgentsLLM agents and tool use → Multimodal and embodied agents
  64. Entropy After </Think> for reasoning model early exitingLLM reasoning → Test-time compute and efficient thinking +1
  65. Training Matryoshka Mixture-of-Experts for Elastic Inference-Time Expert UtilizationMixture-of-experts → MoE large language models
  66. SCUBA: Salesforce Computer Use BenchmarkLLM agents and tool use → GUI and mobile agents
  67. Revealing the Power of Post-Training for Small Language Models via Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
  68. OffTopicEval: When Large Language Models Enter the Wrong Chat, Almost Always!LLM agents and tool use → Agent threats, guardrails and governance
  69. VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world ApplicationsLLM agents and tool use → General LLM agent frameworks and benchmarks
  70. Contrastive Diffusion Guidance for Spatial Inverse ProblemsDiffusion models → Inverse problems and image restoration
  71. dParallel: Learnable Parallel Decoding for dLLMsEfficient LLM inference and serving → Diffusion LLM and MoE inference
  72. The Plot Twist: Jailbreaking Unified Multimodal Models with a Three-Act NarrativeAttackLLM safety and security → Vision-language and text-to-image safety
  73. CreAgentive: An Agent Workflow Driven Multi-Category Creative Generation EngineLLM agents and tool use → Multimodal and embodied agents
  74. Extensions of Robbins-Siegmund Theorem with Applications in Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  75. Post-Training Quantization via Residual Truncation and Zero Suppression for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  76. ACT: Agentic Classification TreeLLM agents and tool use → General LLM agent frameworks and benchmarks
  77. AdaBlock-dLLM: Semantic-Aware Diffusion LLM Inference via Adaptive Block SizeEfficient LLM inference and serving → Diffusion LLM and MoE inference
  78. Ascent Fails to ForgetLLM safety and security → Machine unlearning
  79. MotionRAG: Motion Retrieval-Augmented Image-to-Video GenerationDiffusion models → Video generation
  80. PANDA: Towards Generalist Video Anomaly Detection via Agentic AI EngineerLLM agents and tool use → Software engineering coding agents
  81. Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement LearningLLM reasoning → Knowledge- and tool-augmented reasoning +2
  82. Data-to-Energy Stochastic DynamicsDiffusion models → Diffusion foundations and sampling +1
  83. Your Agent May Misevolve: Emergent Risks in Self-evolving LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  84. EditReward: A Human-Aligned Reward Model for Instruction-Guided Image EditingLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  85. SafeBehavior: Simulating Human-Like Multistage Reasoning to Mitigate Jailbreak Attacks in Large Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
  86. Memory-Driven Self-Improvement for Decision Making with Large Language ModelsSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  87. Kinodynamic Motion Planning for Mobile Robot Navigation across Inconsistent World ModelsWorld models → World models for navigation
  88. SQUARE: Semantic Query-Augmented Fusion and Efficient Batch Reranking for Training-free Zero-Shot Composed Image RetrievalMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  89. COMRES-VLM: Coordinated Multi-Robot Exploration and Search using Vision Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  90. Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in Its Latent ThoughtsLLM reasoning → Test-time compute and efficient thinking +1
  91. Interactive Learning for LLM ReasoningLLM reasoning → Reasoning for agents, planning and code
  92. Feedback Forensics: A Toolkit to Measure AI PersonalityLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  93. Noise-Guided Transport for Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
  94. Flower: A Flow-Matching Solver for Inverse ProblemsDiffusion models → Flow matching, time series and science
  95. ProfVLM: A lightweight video-language model for multi-view proficiency estimationLLM reasoning → Multimodal reasoning +1
  96. PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake DetectionLLM reasoning → Multimodal reasoning
  97. ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot PlanningWorld models → Latent predictive world models
  98. Seeing Space and Motion: Enhancing Latent Actions with Geometric and Dynamic Awareness for Vision-Language-Action ModelsVision-language-action models → Human-video and latent-action pretraining
  99. Beyond Linear Probes: Dynamic Safety Monitoring for Language ModelsLLM safety and security → Safety alignment, refusal and guardrails +1
  100. Interpret, prune and distill Donut : towards lightweight VLMs for VQA on documentMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
All 612
  1. IMG: Calibrating Diffusion Models via Implicit Multimodal GuidanceDiffusion models → Image generation, text-to-image and editing
  2. Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient ReasonersLLM reasoning → Reinforcement learning for reasoning +1
  3. Diversity-Incentivized Exploration for Versatile ReasoningLLM reasoning → Reinforcement learning for reasoning
  4. Human-Centered Evaluation of RAG outputs: a framework and questionnaire for human-AI collaborationRetrieval-augmented generation → RAG pipeline design and evaluation
  5. LLM Agents for Knowledge Discovery in Atomic Layer ProcessingLLM agents and tool use → Medical and scientific domain agents
  6. Toward an Unbiased Collective Memory for Efficient LLM-Based Agentic 6G Cross-Domain ManagementLLM agents and tool use → Agentic AI for wireless networks
  7. Auto-ARGUE: LLM-Based Report Generation EvaluationRetrieval-augmented generation → RAG pipeline design and evaluation
  8. Parallax: Efficient LLM Inference Service over Decentralized EnvironmentEfficient LLM inference and serving → Serving systems and request scheduling
  9. Alignment-Aware DecodingLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  10. Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  11. A Field Guide to Deploying AI Agents in Clinical PracticeLLM agents and tool use → Medical and scientific domain agents
  12. OWL: Geometry-Aware Spatial Reasoning for Audio Large Language ModelsLLM reasoning → Audio-language model reasoning
  13. Accelerating Transformers in Online RLDeep reinforcement learning methods → RL for robot locomotion and manipulation
  14. The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent SystemsLLM agents and tool use → Social simulation and multi-agent debate
  15. Clip-Low Increases Entropy and Clip-High Decreases Entropy in Reinforcement Learning of Large Language ModelsLLM reasoning → Reinforcement learning for reasoning
  16. Agent-based code generation for the Gammapy frameworkLLM agents and tool use → Software engineering coding agents
  17. AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language ModelsLLM agents and tool use → Agent threats, guardrails and governance +1
  18. EVODiff: Entropy-aware Variance Optimized Diffusion InferenceDiffusion models → Diffusion foundations and sampling
  19. Text-to-Scene with Large Reasoning ModelsLLM reasoning → Spatial and embodied reasoning
  20. Evaluating the Use of Large Language Models as Synthetic Social Agents in Social Science ResearchLLM agents and tool use → Social simulation and multi-agent debate
  21. Limited Preference Data? Learning Better Reward Model with Latent Space SynthesisLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  22. Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for RecommendationDiffusion models → Diffusion recommenders
  23. DyFlow: Dynamic Workflow Framework for Agentic ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  24. RE-Searcher: Robust Agentic Search with Goal-oriented Planning and Self-reflectionLLM agents and tool use → Web, search, and research agents
  25. Unspoken Hints: Accuracy Without Acknowledgement in LLM ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  26. PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-ResolutionDiffusion models → Inverse problems and image restoration
  27. RAGferee: Building Contextual Reward Models for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval +1
  28. New Fourth-Order Grayscale Indicator-Based Telegraph Diffusion Model for Image DespecklingDiffusion models → Diffusion foundations and sampling
  29. AgenticIQA: An Agentic Framework for Adaptive and Interpretable Image Quality AssessmentLLM agents and tool use → Multimodal and embodied agents
  30. Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State AccessDeep reinforcement learning methods → RL theory and sample complexity
  31. VRWKV-Editor: Reducing quadratic complexity in transformer-based video editingDiffusion models → Video generation
  32. R-Log: Incentivizing Log Analysis Capability in LLMs via Reasoning-based Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  33. Scalable and Robust LLM Unlearning by Correcting Responses with Retrieved ExclusionsLLM safety and security → Machine unlearning
  34. MUVLA: Learning to Explore Object Navigation via Map UnderstandingVision-language-action models → 3D and spatial-aware VLA
  35. RoRecomp: Enhancing Reasoning Efficiency via Rollout Response Recomposition in Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  36. NuRisk: A Visual Question Answering Dataset for Agent-Level Risk Assessment in Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +2
  37. Boosting Process-Correct CoT Reasoning by Modeling Solvability of Multiple-Choice QALLM reasoning → Prompting and chain-of-thought reasoning
  38. Steer Away From Mode Collisions: Improving Composition In Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  39. UniMMAD: Unified Multi-Modal and Multi-Class Anomaly Detection via MoE-Driven Feature DecompressionMixture-of-experts → Vision mixture-of-experts
  40. Preventing Prompt Injection with Type-Directed Privilege SeparationLLM agents and tool use → Agent threats, guardrails and governance +1
  41. VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMsLLM reasoning → Multimodal reasoning +1
  42. Understanding the Mixture-of-Experts with Nadaraya-Watson KernelMixture-of-experts → MoE theory and gating functions
  43. Mem-α: Learning Memory Construction via Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  44. LLaVAShield: Safeguarding Multimodal Multi-Turn Dialogues in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  45. Red Teaming Program Repair Agents: When Correct Patches can Hide VulnerabilitiesLLM agents and tool use → Agent threats, guardrails and governance +1
  46. Multimodal LLM With Hierarchical Mixture-of-Experts for VQA on 3D Brain MRIMultimodal LLMs / vision-language models → Medical vision-language models +1
  47. SafeMind: Benchmarking and Mitigating Safety Risks in Embodied LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  48. Efficient On-Policy Reinforcement Learning via Exploration of Sparse Parameter SpaceDeep reinforcement learning methods → RL theory and sample complexity
  49. Lita: Light Agent Uncovers the Agentic Coding Capabilities of LLMsLLM agents and tool use → Software engineering coding agents
  50. DeepSketcher: Internalizing Visual Manipulation for Multimodal ReasoningLLM reasoning → Multimodal reasoning +1
  51. MAPLE: Multi-scale Attribute-enhanced Prompt Learning for Few-shot Whole Slide Image ClassificationMultimodal LLMs / vision-language models → Medical vision-language models
  52. SAIL: SRAM-Accelerated LLM Inference System with Lookup-Table-based GEMVEfficient LLM inference and serving → Serving systems and request scheduling
  53. MuSLR: Multimodal Symbolic Logical ReasoningLLM reasoning → Multimodal reasoning
  54. More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  55. Training-Free Reward-Guided Image Editing via Trajectory Optimal ControlDiffusion models → Image generation, text-to-image and editing
  56. Believing without Seeing: Quality Scores for Contextualizing Vision-Language Model ExplanationsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  57. ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking AttackLLM safety and security → Jailbreaking
  58. RAE: A Neural Network Dimensionality Reduction Method for Nearest Neighbors Preservation in Vector SearchRetrieval-augmented generation → Vector search and ANN indexes
  59. Chain-in-Tree: Back to Sequential Reasoning in LLM Tree SearchLLM reasoning → Test-time compute and efficient thinking
  60. Overthinking Reduction with Decoupled Rewards and Curriculum Data SchedulingLLM reasoning → Test-time compute and efficient thinking
  61. Act to See, See to Act: Diffusion-Driven Perception-Action Interplay for Adaptive PoliciesDiffusion models → Diffusion and flow policies for robotics +1
  62. VELA: An LLM-Hybrid-as-a-Judge Approach for Evaluating Long Image CaptionsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  63. ReTAG: Retrieval-Enhanced, Topic-Augmented Graph-Based Global SensemakingLLM reasoning → Knowledge- and tool-augmented reasoning
  64. Logo-VGR: Visual Grounded Reasoning for Open-world Logo RecognitionLLM reasoning → Multimodal reasoning +1
  65. Learning to Reason as Action Abstractions with Scalable Mid-Training RLLLM reasoning → Reinforcement learning for reasoning
  66. Improving Sampling Efficiency in RLVR through Adaptive Rollout and Response ReuseLLM reasoning → Reinforcement learning for reasoning
  67. Point-It-Out: Benchmarking Embodied Reasoning for Vision Language Models in Multi-Stage Visual GroundingLLM reasoning → Spatial and embodied reasoning +1
  68. PUREVQ-GAN: Defending Data Poisoning Attacks through Vector-Quantized BottlenecksLLM safety and security → Backdoor and data poisoning attacks
  69. Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and RankingMultimodal LLMs / vision-language models → Image editing and quality assessment +1
  70. Planner-R1: Reward Shaping Enables Efficient Agentic RL with Smaller LLMsLLM agents and tool use → Reinforcement learning for LLM agents
  71. Editable Noise Map Inversion: Encoding Target-image into Noise For High-Fidelity Image ManipulationDiffusion models → Image generation, text-to-image and editing
  72. Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image PairsDiffusion models → Diffusion and flow policies for robotics +1
  73. OPPO: Accelerating PPO-based RLHF via Pipeline OverlapLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  74. Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post TrainingLLM reasoning → Test-time compute and efficient thinking
  75. NePTune: A Neuro-Pythonic Framework for Tunable Compositional Reasoning on Vision-LanguageLLM reasoning → Multimodal reasoning +1
  76. SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential ModelingDeep reinforcement learning methods → RL with diffusion and flow models
  77. Cooperative Autonomous Driving in Diverse Behavioral Traffic: A Heterogeneous Graph Reinforcement Learning ApproachEnd-to-end autonomous driving → Cooperative and V2X driving +1
  78. ART-VITON: Measurement-Guided Latent Diffusion for Artifact-Free Virtual Try-OnDiffusion models → 3D, point cloud and scene generation
  79. FinCap: Topic-Aligned Captions for Short-Form Financial YouTube VideosMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  80. Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation SpaceLLM safety and security → Machine unlearning
  81. Think Less, Label Better: Multi-Stage Domain-Grounded Synthetic Data Generation for Fine-Tuning Large Language Models in TelecommunicationsLLM reasoning → Reasoning benchmarks and evaluation +1
  82. CATCH: A Novel Data Synthesis Framework for High Therapy Fidelity and Memory-Driven Planning Chain of Thought in AI CounselingLLM reasoning → Clinical and biomedical applications +1
  83. LaTo: Landmark-tokenized Diffusion Transformer for Fine-grained Human Face EditingDiffusion models → Image generation, text-to-image and editing
  84. Boundary-to-Region Supervision for Offline Safe Reinforcement LearningOffline RL and imitation learning from data → Safe offline RL
  85. Atomic Thinking of LLMs: Decoupling and Exploring Mathematical Reasoning AbilitiesLLM reasoning → Mathematical reasoning
  86. VLA Model Post-Training via Action-Chunked PPO and Self Behavior CloningVision-language-action models → Reinforcement learning and post-training
  87. Importance Sampling for Multi-Negative Multimodal Direct Preference OptimizationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  88. Reweighted Flow Matching via Unbalanced OT for Label-free Long-tailed GenerationDiffusion models → Flow matching, time series and science
  89. Expert Merging: Model Merging with Unsupervised Expert Alignment and Importance-Guided Layer ChunkingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  90. How Diffusion Models MemorizeDiffusion models → Diffusion foundations and sampling
  91. AIM-CoT: Active Information-driven Multimodal Chain-of-Thought for Vision-Language ReasoningLLM reasoning → Multimodal reasoning
  92. ScheduleMe: Multi-Agent Calendar AssistantLLM agents and tool use → General LLM agent frameworks and benchmarks
  93. Collaborative Compression for Large-Scale MoE Deployment on EdgeMixture-of-experts → MoE large language models
  94. EXP-CAM: Explanation Generation and Circuit Discovery Using Classifier Activation MatchingMechanistic interpretability → Circuits and mechanistic analysis
  95. LD-MoLE: Learnable Dynamic Routing for Mixture of LoRA ExpertsMixture-of-experts → Mixture of LoRA experts
  96. dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-ThoughtLLM reasoning → Spatial and embodied reasoning +1
  97. Massively Multimodal Foundation Models: A Framework for Capturing Interactions with Specialized Mixture-of-ExpertsMixture-of-experts → Medical and biomedical MoE
  98. Mitigating Biases in Language Models via Bias UnlearningLLM safety and security → Safety alignment, refusal and guardrails
  99. SING-SQL: A Synthetic Data Generation Framework for In-Domain Text-to-SQL TranslationSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
  100. LTA-L2S: Lexical Tone-Aware Lip-to-Speech Synthesis for Mandarin with Cross-Lingual Transfer LearningDiffusion models → Audio, speech and music
  101. GroundSight: Augmenting Vision-Language Models with Grounding Information and De-hallucinationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  102. Nudging the Boundaries of LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  103. DescribeEarth: Describe Anything for Remote Sensing ImagesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  104. Swift: An Autoregressive Consistency Model for Efficient Weather ForecastingDiffusion models → Flow matching, time series and science
  105. STAC: When Innocent Tools Form Dangerous Chains for LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  106. LMOD+: A Comprehensive Multimodal Dataset and Benchmark for Developing and Evaluating Multimodal Large Language Models in OphthalmologyMultimodal LLMs / vision-language models → Medical vision-language models
  107. SMS: Self-supervised Model Seeding for Verification of Machine UnlearningLLM safety and security → Machine unlearning
  108. A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice ExperimentsLLM agents and tool use → Social simulation and multi-agent debate
  109. Towards Real-World Validity in Generative AI Benchmarks: Understanding and Designing Domain-Centered Evaluations for Journalism Practitioners
  110. Learn2Drive: A neural network-based framework for socially compliant automated vehicle control
  111. A phase-aware AI car-following model for electric vehicles with adaptive cruise control: Development and validation using real-world data
  112. Automated Pest Counting in Water Traps through Active Robotic Stirring for Occlusion Handling
  113. Covariance Matrix Construction with Preprocessing-Based Spatial Sampling for Robust Adaptive Beamforming
  114. Bias-Aware AI Chatbot for Engineering Advising at the University of Maryland A. James Clark School of Engineering
  115. MultiFair: Multimodal Balanced Fairness-Aware Medical Classification with Dual-Level Gradient Modulation
  116. Milestone Determination for Autonomous Railway Operation
  117. Layerwise Federated Learning for Heterogeneous Quantum Clients using Quorus
  118. Submodular Context Partitioning and Compression for In-Context Learning
  119. Automated Alignment of Math Items to Content Standards in Large-Scale Assessments Using Language Models
  120. Advancing Automated Spatio-Semantic Analysis in Picture Description Using Language Models
  121. Artificial Intelligence for Cost-Aware Resource Prediction in Big Data Pipelines
  122. Generalization of Fine-Tuned Uncertainty Communication and Metacognition in Large Language Models
  123. A Scalable AI Driven, IoT Integrated Cognitive Digital Twin for Multi-Modal Neuro-Oncological Prognostics and Tumor Kinetics Prediction using Enhanced Vision Transformer and XAI
  124. CARE: Cognitive-reasoning Augmented Reinforcement for Emotional Support Conversation
  125. From Camera-Based Sensing to Reasoning: A Comprehensive Review Toward Proactive Vulnerable Road User Safety
  126. Scaling Laws Revisited: Modeling the Role of Data Quality in Language Model Pretraining
  127. Universal Beta Splatting
  128. Predicting Effects, Missing Distributions: Evaluating LLMs as Human Behavior Simulators in Operations Management
  129. Thin Bridges for Drug Text Alignment: Lightweight Contrastive Learning for Target Specific Drug Retrieval
  130. Creative synthesis of kinematic mechanisms
  131. Atlas-free Brain Network Transformer
  132. Machine Learning Workflows in Climate Modeling: Design Patterns and Insights from Case Studies
  133. Machine Learning and Control: Foundations, Advances, and Perspectives
  134. Dynamic Meta-Learning for Adaptive XGBoost-Neural Ensembles
  135. LLM-Generated Samples for Android Malware Detection
  136. Scaling Homomorphic Applications in Deployment
  137. Emergent evaluation hubs in a decentralizing large language model ecosystem
  138. Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation
  139. Evaluation Sheet for Deep Research: A Use Case for Academic Survey Writing
  140. An Analysis of the New EU AI Act and A Proposed Standardization Framework for Machine Learning Fairness
  141. Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning
  142. LLM Based Sentiment Classification From Bangladesh E-Commerce Reviews
  143. TraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Models
  144. Neural Hamilton--Jacobi Characteristic Flows for Optimal Transport
  145. AReUReDi: Annealed Rectified Updates for Refining Discrete Flows with Multi-Objective Guidance
  146. Initial Distribution Sensitivity of Constrained Markov Decision Processes
  147. In-Context Curiosity: Distilling Exploration for Decision-Pretrained Transformers on Bandit Tasks
  148. Cutting the Skip: Training Residual-Free Transformers
  149. Navigating the Synchrony-Stability Frontier in Adaptive Chatbots
  150. Structural Refinement of Bayesian Networks for Efficient Model Parameterisation
  151. When Hallucination Costs Millions: Benchmarking AI Agents in High-Stakes Adversarial Financial Markets
  152. QSearchNet: A Quantum Walk Search Framework for Link Prediction
  153. Which Programming Language and Model Work Best With LLM-as-a-Judge For Code Retrieval?
  154. Privately Estimating Black-Box Statistics
  155. A Framework for Selection of Machine Learning Algorithms Based on Performance Metrices and Akaike Information Criteria in Healthcare, Telecommunication, and Marketing Sector
  156. MAVUL: Multi-Agent Vulnerability Detection via Contextual Reasoning and Interactive Refinement
  157. Large Language Models Can Perform Automatic Modulation Classification via Discretized Self-supervised Candidate Retrieval
  158. Motion In-Betweening for Densely Interacting Characters
  159. Digital Domination: A Case for Republican Liberty in Artificial Intelligence
  160. Robust Federated Inference
  161. Lipschitz Bandits with Stochastic Delayed Feedback
  162. BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models
  163. Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity
  164. Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detection
  165. ICL Optimized Fragility
  166. Malliavin Calculus with Weak Derivatives for Counterfactual Stochastic Optimization
  167. Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT
  168. o-MEGA: Optimized Methods for Explanation Generation and Analysis
  169. Data driven approaches in nanophotonics: A review of AI-enabled metadevices
  170. Electron neural closure for turbulent magnetosheath simulations: energy channels
  171. ReEvalMed: Rethinking Medical Report Evaluation by Aligning Metrics with Real-World Clinical Judgment
  172. SLogic: Subgraph-Informed Logical Rule Learning for Knowledge Graph Completion
  173. SafePassage: High-Fidelity Information Extraction with Black Box LLMs
  174. MAGIC-MASK: Multi-Agent Guided Inter-Agent Collaboration with Mask-Based Explainability for Reinforcement Learning
  175. Efficient Layer-wise LLM Fine-tuning for Revision Intention Prediction
  176. Baseline Systems For The 2025 Low-Resource Audio Codec Challenge
  177. Learning Energy-based Variational Latent Prior for VAEs
  178. Delayed Attention Training Improves Length Generalization in Transformer--RNN Hybrids
  179. DReS: Dual Reconstruction Smoothing for Functional Regularization
  180. Board gender diversity and emissions performance: Insights from panel regressions, machine learning, and explainable AI
  181. Reward driven discovery of the optimal microstructure representations with invariant variational autoencoders
  182. SecureBERT 2.0: Advanced Language Model for Cybersecurity Intelligence
  183. Per-example gradients: a new frontier for understanding and improving optimizers
  184. Differentiable Autoencoding Neural Operator for Interpretable and Integrable Latent Space Modeling
  185. BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses
  186. TGPO: Temporal Grounded Policy Optimization for Signal Temporal Logic Tasks
  187. Learning from the electronic structure of molecules across the periodic table
  188. LoRAFusion: Efficient LoRA Fine-Tuning for LLMs
  189. RouterArena: An Open Platform for Comprehensive Comparison of LLM Routers
  190. Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation
  191. Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls
  192. A Systematic Study of Large Language Models for Task and Motion Planning With PDDLStream
  193. CHAI: Command Hijacking against embodied AI
  194. PrimeX: A Dataset of Worldview, Opinion, and Explanation
  195. DRBench: A Realistic Benchmark for Enterprise Deep Research
  196. Quantum reservoir computing in Jaynes-Cummings models: Nonlinear memory and time-series prediction
  197. Privacy-Preserving Learning-Augmented Data Structures
  198. Partial Identification Approach to Counterfactual Fairness Assessment
  199. AuditAgent: Expert-Guided Multi-Agent Reasoning for Cross-Document Fraudulent Evidence Discovery
  200. Stealing AI Model Weights Through Covert Communication Channels
  201. Improved Hyperspectral Anomaly Detection via Unsupervised Subspace Modeling in the Signed Cumulative Distribution Transform Domain
  202. Optimizing What Matters: AUC-Driven Learning for Robust Neural Retrieval
  203. Nonparametric Identification of Latent Concepts
  204. Large Language Models Inference Engines based on Spiking Neural Networks
  205. BigBang-Proton Technical Report: Next-Word-Prediction is Scientific Multitask Learner
  206. Approximately Unimodal Likelihood Models for Ordinal Regression
  207. Revealing the temporal dynamics of antibiotic anomalies in the infant gut microbiome with neural jump ODEs
  208. Behavioural Classification in C. elegans: a Spatio-Temporal Analysis of Locomotion
  209. Towards a Framework for Supporting the Ethical and Regulatory Certification of AI Systems
  210. Enhancing Certifiable Semantic Robustness via Robust Pruning of Deep Neural Networks
  211. SoREX: Towards Self-Explainable Social Recommendation with Relevant Ego-Path Extraction
  212. Directed Information γ-covering: An Information-Theoretic Framework for Context Engineering
  213. Private Learning of Littlestone Classes, Revisited
  214. NeurIPS should lead scientific consensus on AI policy
  215. TTT3R: 3D Reconstruction as Test-Time Training
  216. Convergence and Divergence of Language Models under Different Random Seeds
  217. SPATA: Systematic Pattern Analysis for Detailed and Transparent Data Cards
  218. Benchmarking Egocentric Visual-Inertial SLAM at City Scale
  219. AccidentBench: Benchmarking Multimodal Understanding and Reasoning in Vehicle Accidents and Beyond
  220. Scaling Spoken Language Models with Syllabic Speech Tokenization
  221. Branching Out: Broadening AI Measurement and Evaluation with Measurement Trees
  222. Learning Generalizable Shape Completion with SIM(3) Equivariance
  223. Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training
  224. HART: Human Aligned Reconstruction Transformer
  225. Searching the Internet for Challenging Benchmarks at Scale
  226. DA2: Depth Anything in Any Direction
  227. Hy-Facial: Hybrid Feature Extraction by Dimensionality Reduction Methods for Enhanced Facial Expression Classification
  228. Uncertainty Quantification for Regression using Proper Scoring Rules
  229. Video Object Segmentation-Aware Audio Generation
  230. DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively
  231. When LLMs Benchmark Themselves: Deconstructing Self-Bias in Automated Evaluation
  232. DiffCamera: Arbitrary Refocusing on Images
  233. Are Robust LLM Fingerprints Adversarially Robust?
  234. Generating Difficult-to-Translate Texts
  235. Autoproof: Automated Segmentation Proofreading for Connectomics
  236. Source Separation for A Cappella Music
  237. Importance of localized dilatation and distensibility in identifying determinants of thoracic aortic aneurysm with neural operators
  238. AI-assisted Advanced Propellant Development for Electric Propulsion
  239. Parametric Neural Amp Modeling with Active Learning
  240. DeepProv: Behavioral Characterization and Repair of Neural Networks via Inference Provenance Graph Analysis
  241. Estimating Dimensionality of Neural Representations from Finite Samples
  242. Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generation
  243. Pretrain-Test Task Alignment Governs Generalization in In-Context Learning
  244. Automated and Scalable SEM Image Analysis of Perovskite Solar Cell Materials via a Deep Segmentation Framework
  245. Bayesian Influence Functions for Hessian-Free Data Attribution
  246. The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models
  247. TASP: Topology-aware Sequence Parallelism
  248. The Loss Kernel: A Geometric Probe for Deep Learning Interpretability
  249. Rearchitecting Datacenter Lifecycle for AI: A TCO-Driven Framework
  250. Machine-Learning Driven Load Shedding to Mitigate Instability Attacks in Power Grids
  251. TAP: Two-Stage Adaptive Personalization of Multi-Task and Multi-Modal Foundation Models in Federated Learning
  252. MUSE-Explainer: Counterfactual Explanations for Symbolic Music Graph Classification Models
  253. BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMs
  254. Signal-Aware Workload Shifting Algorithms with Uncertainty-Quantified Predictors
  255. The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain
  256. GastroViT: A Vision Transformer Based Ensemble Learning Approach for Gastrointestinal Disease Classification with Grad CAM & SHAP Visualization
  257. Indoor/Outdoor Spectrum Sharing Enabled by GNSS-based Classifiers
  258. Equivariance by Local Canonicalization: A Matter of Representation
  259. DEPTHOR++: Robust Depth Enhancement from a Real-World Lightweight dToF and RGB Guidance
  260. Combining Knowledge Graphs and NLP to Analyze Instant Messaging Data in Criminal Investigations
  261. CBAM Integrated Attention Driven Model For Betel Leaf Diseases Classification With Explainable AI
  262. TVS Sidekick: Challenges and Practical Insights from Deploying Large Language Models in the Enterprise
  263. Regression Language Models for Code
  264. The Average Patient Fallacy
  265. On Deepfake Voice Detection -- It's All in the Presentation
  266. DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick
  267. fev-bench: A Realistic Benchmark for Time Series Forecasting
  268. Extreme Self-Preference in Language Models
  269. Zero-Shot Decentralized Federated Learning
  270. Attention over Scene Graphs: Indoor Scene Representations Toward CSAI Classification
  271. Stylos: Multi-View 3D Stylization with Single-Forward Gaussian Splatting
  272. Multi-View Camera System for Variant-Aware Autonomous Vehicle Inspection and Defect Detection
  273. Stabilization of nonlinear systems with unknown delays via delay-adaptive neural operator approximate predictors
  274. Transformer Classification of Breast Lesions: The BreastDCEDL_AMBL Benchmark Dataset and 0.92 AUC Baseline
  275. Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search
  276. Text-Based Approaches to Item Alignment to Content Standards in Large-Scale Reading & Writing Tests
  277. An Orthogonal Learner for Individualized Outcomes in Markov Decision Processes
  278. OntoAligner Meets Knowledge Graph Embedding Aligners
  279. Automatic Fact-checking in English and Telugu
  280. PRISM: Progressive Rain removal with Integrated State-space Modeling
  281. TrackFormers Part 2: Enhanced Transformer-Based Models for High-Energy Physics Track Reconstruction
  282. An Annotation Scheme for Factuality and its Application to Parliamentary Proceedings
  283. Refine Drugs, Don't Complete Them: Uniform-Source Discrete Flows for Fragment-Based Drug Discovery
  284. SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From
  285. Communication-Efficient and Accurate Approach for Aggregation in Federated Low-Rank Adaptation
  286. Image-Difficulty-Aware Evaluation of Super-Resolution Models
  287. Are neural scaling laws leading quantum chemistry astray?
  288. Game-Time: Evaluating Temporal Dynamics in Spoken Language Models
  289. MR2-Bench: Going Beyond Matching to Reasoning in Multimodal Retrieval
  290. MC-GNNAS-Dock: Multi-criteria GNN-based Algorithm Selection for Molecular Docking
  291. ScalingAR: Scaling Confidence for Autoregressive Image Generation
  292. SDA-PLANNER: State-Dependency Aware Adaptive Planner for Embodied Task Planning
  293. Vector-Valued Reproducing Kernel Banach Spaces for Neural Networks and Operators
  294. TimeScope: Towards Task-Oriented Temporal Grounding In Long Videos
  295. LLM-Assisted Emergency Triage Benchmark: Bridging Hospital-Rich and MCI-Like Field Simulation
  296. SoK: Systematic analysis of adversarial threats against deep learning approaches for autonomous anomaly detection systems in SDN-IoT networks
  297. Uncovering Zero-Shot Generalization Gaps in Time-Series Foundation Models Using Real-World Videos
  298. FedMuon: Federated Learning with Bias-corrected LMO-based Optimization
  299. TrackCore-F: Deploying Transformer-Based Subatomic Particle Tracking on FPGAs
  300. AI Playing Business Games: Benchmarking Large Language Models on Managerial Decision-Making in Dynamic Simulations
  301. TAU: A Benchmark for Cultural Sound Understanding Beyond Semantics
  302. Fast-dLLM v2: Efficient Block-Diffusion LLM
  303. A Generalized Information Bottleneck Theory of Deep Learning
  304. Continuous Space-Time Video Super-Resolution with 3D Fourier Fields
  305. ACE: Adapting sampling for Counterfactual Explanations
  306. A Review on Single-Problem Multi-Attempt Heuristic Optimization
  307. One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient
  308. Ultra-Reliable Risk-Aggregated Sum Rate Maximization via Model-Aided Deep Learning
  309. Attribution-Guided Decoding
  310. QUARTZ : QA-based Unsupervised Abstractive Refinement for Task-oriented Dialogue Summarization
  311. NeuroTTT: Bridging Pretraining-Downstream Task Misalignment in EEG Foundation Models via Test-Time Training
  312. Tuning the Tuner: Introducing Hyperparameter Optimization for Auto-Tuning
  313. Representation-Based Data Quality Audits for Audio
  314. Reframing Generative Models for Physical Systems using Stochastic Interpolants
  315. Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization
  316. Cat: Post-Training Quantization Error Reduction via Cluster-based Affine Transformation
  317. Optimizing Speech Language Models for Acoustic Consistency
  318. Wasserstein Distributionally Robust Optimization Through the Lens of Structural Causal Models and Individual Fairness
  319. Staged Event Trees for Transparent Treatment Effect Estimation
  320. Why is topology hard to learn?
  321. EnScale: Temporally-consistent multivariate generative downscaling via proper scoring rules
  322. SlimPack: Fine-Grained Asymmetric Packing for Balanced and Efficient Variable-Length LLM Training
  323. Finetune Once: Decoupling General & Domain Learning with Dynamic Boosted Annealing
  324. From Fragile to Certified: Wasserstein Audits of Group Fairness Under Distribution Shift
  325. Sandbagging in a Simple Survival Bandit Problem
  326. Machine Learning Detection of Lithium Plating in Lithium-ion Cells: A Gaussian Process Approach
  327. 3DiFACE: Synthesizing and Editing Holistic 3D Facial Animation
  328. Hybrid Quantum-Classical Optimisation of Traveling Salesperson Problem
  329. Generalized Fine-Grained Category Discovery with Multi-Granularity Conceptual Experts
  330. An Experimental Study on Generating Plausible Textual Explanations for Video Summarization
  331. Type-Less yet Type-Aware Inductive Link Prediction with Pretrained Language Models
  332. Marginal Flow: a flexible and efficient framework for density estimation
  333. Parameterizing Dataset Distillation via Gaussian Splatting
  334. Benchmarking Deep Learning Convolutions on Energy-constrained CPUs
  335. Comparative Analysis of Ant Colony Optimization and Google OR-Tools for Solving the Open Capacitated Vehicle Routing Problem in Logistics
  336. TSalV360: A Method and Dataset for Text-driven Saliency Detection in 360-Degrees Videos
  337. The silence of the weights: a structural pruning strategy for attention-based audio signal architectures with second order metrics
  338. Self-supervised learning for phase retrieval
  339. VietBinoculars: A Zero-Shot Approach for Detecting Vietnamese LLM-Generated Text
  340. Optimizing Indoor Environmental Quality in Smart Buildings Using Deep Learning
  341. PDE Solvers Should Be Local: Fast, Stable Rollouts with Learned Local Stencils
  342. AttriGen: Automated Multi-Attribute Annotation for Blood Cell Datasets
  343. Explaining novel senses using definition generation with open language models
  344. Benchmarking Diarization Models
  345. Spectral gap of Metropolis-within-Gibbs under log-concavity
  346. Neighbor-aware informal settlement mapping with graph convolutional networks
  347. 'Too much alignment; not enough culture': Re-balancing cultural alignment practices in LLMs
  348. Beyond Overall Accuracy: Pose- and Occlusion-driven Fairness Analysis in Pedestrian Detection for Autonomous Driving
  349. 90% Faster, 100% Code-Free: MLLM-Driven Zero-Code 3D Game Development
  350. MGen: Millions of Naturally Occurring Generics in Context
  351. Towards Continual Expansion of Data Coverage: Automatic Text-guided Edge-case Synthesis
  352. Entropy Guided Dynamic Patch Segmentation for Time Series Transformers
  353. Bubble, Bubble, AI's Rumble: Why Global Financial Regulatory Incident Reporting is Our Shield Against Systemic Stumbles
  354. Non-Vacuous Generalization Bounds: Can Rescaling Invariances Help?
  355. Ordinal Label-Distribution Learning with Constrained Asymmetric Priors for Imbalanced Retinal Grading
  356. LMILAtt: A Deep Learning Model for Depression Detection from Social Media Users Enhanced by Multi-Instance Learning Based on Attention Mechanism
  357. Leveraging AI modelling for FDS with Simvue: monitor and optimise for more sustainable simulations
  358. CliniBench: A Clinical Outcome Prediction Benchmark for Generative and Encoder-Based Language Models
  359. Domain-Aware Hyperdimensional Computing for Edge Smart Manufacturing
  360. MEDAKA: Construction of Biomedical Knowledge Graphs Using Large Language Models
  361. EchoGen: Generating Visual Echoes in Any Scene via Feed-Forward Subject-Driven Auto-Regressive Model
  362. Vocabulary Customization for Efficient Domain-Specific LLM Deployment
  363. AGOCS -- Accurate Google Cloud Simulator Framework
  364. UncertainGen: Uncertainty-Aware Representations of DNA Sequences for Metagenomic Binning
  365. Enhancing PINN Performance Through Lie Symmetry Group
  366. Autonomous Multi-Robot Infrastructure for AI-Enabled Healthcare Delivery and Diagnostics
  367. End-to-End Aspect-Guided Review Summarization at Scale
  368. On Computing Top-k Simple Shortest Paths from a Single Source
  369. Reinforced Strategy Optimization for Conversational Recommender Systems via Network-of-Experts
  370. Hybrid Dual-Batch and Cyclic Progressive Learning for Efficient Distributed Training
  371. Predicting Penalty Kick Direction Using Multi-Modal Deep Learning with Pose-Guided Attention
  372. Easy3D-Labels: Supervising Semantic Occupancy Estimation with 3D Pseudo-Labels for Automotive Perception
  373. IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation
  374. The Silent Judge: Unacknowledged Shortcut Bias in LLM-as-a-Judge
  375. Geometric Learning of Canonical Parameterizations of 2D-curves
  376. Multi-modal Liver Segmentation and Fibrosis Staging Using Real-world MRI Images
  377. Real-time Noise Detection and Classification in Single-Channel EEG: A Lightweight Machine Learning Approach for EMG, White Noise, and EOG Artifacts
  378. GaussEdit: Adaptive 3D Scene Editing with Text and Image Prompts
  379. CEAID: Benchmark of Multilingual Machine-Generated Text Detection Methods for Central European Languages
  380. DGM4+: Dataset Extension for Global Scene Inconsistency
  381. Scaling Up Temporal Domain Generalization via Temporal Experts Averaging
  382. Nonparametric inference under shape constraints: past, present and future
  383. SGS: Segmentation-Guided Scoring for Global Scene Inconsistencies
  384. RE2: Improving Chinese Grammatical Error Correction via Retrieving Appropriate Examples with Explanation
  385. CoLLM-NAS: Collaborative Large Language Models for Efficient Knowledge-Guided Neural Architecture Search
  386. SeMoBridge: Semantic Modality Bridge for Efficient Few-Shot Adaptation of CLIP
  387. Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification
  388. Muon Outperforms Adam in Tail-End Associative Memory Learning
  389. Causally Guided Gaussian Perturbations for Out-Of-Distribution Generalization in Medical Imaging
  390. FITS: Towards an AI-Driven Fashion Information Tool for Sustainability
  391. GeoLink: Empowering Remote Sensing Foundation Model with OpenStreetMap Data
  392. Indirect Attention: Turning Context Misalignment into a Feature
  393. SETR: A Two-Stage Semantic-Enhanced Framework for Zero-Shot Composed Image Retrieval
  394. PFDepth: Heterogeneous Pinhole-Fisheye Joint Depth Estimation via Distortion-aware Gaussian-Splatted Volumetric Fusion
  395. MARS: Sound Generation via Multi-Channel Autoregression on Spectrograms
  396. BALLAST: Bayesian Active Learning with Look-ahead Amendment for Sea-drifter Trajectories under Spatio-Temporal Vector Fields
  397. Learning Egocentric In-Hand Object Segmentation through Weak Supervision from Human Narrations
  398. Scaling Equilibrium Propagation to Deeper Neural Network Architectures
  399. Towards Human Engagement with Realistic AI Combat Pilots
  400. CAST: Continuous and Differentiable Semi-Structured Sparsity-Aware Training for Large Language Models
  401. MHINDR -- a DSM5 based mental health diagnosis and recommendation framework using LLM
  402. Towards Unified Multimodal Misinformation Detection in Social Media: A Benchmark Dataset and Baseline
  403. Towards Reliable and Holistic Visual In-Context Learning Prompt Selection
  404. Exact Solutions to the Quantum Schr"odinger Bridge Problem
  405. Reconcile Certified Robustness and Accuracy for DNN-based Smoothed Majority Vote Classifier
  406. Data-Free Continual Learning of Server Models in Model-Heterogeneous Cloud-Device Collaboration
  407. PinPoint3D: Fine-Grained 3D Part Segmentation from a Few Clicks
  408. A Multi-purpose Tracking Framework for Salmon Welfare Monitoring in Challenging Environments
  409. Reevaluating Convolutional Neural Networks for Spectral Analysis: A Focus on Raman Spectroscopy
  410. Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation
  411. Reliability Crisis of Reference-free Metrics for Grammatical Error Correction
  412. AIM: Adaptive Intervention for Deep Multi-task Learning of Molecular Properties
  413. Automated Model Discovery via Multi-modal & Multi-step Pipeline
  414. From MNIST to ImageNet: Understanding the Scalability Boundaries of Differentiable Logic Gate Networks
  415. Quantitative Evaluation of KIRETT Wearable Demonstrator for Rescue Operations
  416. The Impact of Scaling Training Data on Adversarial Robustness
  417. KIRETT: Smart Integration of Vital Signs Data for Intelligent Decision Support in Rescue Scenarios
  418. DeepJSONEval: Benchmarking Complex Nested JSON Data Mining for Large Language Models
  419. Accelerating LLM Inference with Precomputed Query Storage
  420. Bringing Emerging Architectures to Sequence Labeling in NLP
  421. ReNF: Rethinking the Design of Neural Long-Term Time Series Forecasters
  422. Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation
  423. User-Centric Communication Service Provision for Edge-Assisted Mobile Augmented Reality
  424. PerQ: Efficient Evaluation of Multilingual Text Personalization Quality
  425. RoleConflictBench: A Benchmark of Role Conflict Scenarios for Evaluating LLMs' Contextual Sensitivity
  426. scUnified: An AI-Ready Standardized Resource for Single-Cell RNA Sequencing Analysis
  427. ASR Under Noise: Exploring Robustness for Sundanese and Javanese
  428. ReFACT: A Benchmark for Scientific Confabulation Detection with Positional Error Annotations
  429. CIMNAS: A Joint Framework for Compute-In-Memory-Aware Neural Architecture Search
  430. LiDAR Point Cloud Colourisation Using Multi-Camera Fusion and Low-Light Image Enhancement
  431. Aging Decline in Basketball Career Trend Prediction Based on Machine Learning and LSTM Model
  432. Vector sketch animation generation with differentiable motion trajectories
  433. PatchEAD: Unifying Industrial Visual Prompting Frameworks for Patch-Exclusive Anomaly Detection
  434. RL-Guided Data Selection for Language Model Finetuning
  435. Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
  436. HiStyle: Hierarchical Style Embedding Predictor for Text-Prompt-Guided Controllable Speech Synthesis
  437. S2FS: Spatially-Aware Separability-Driven Feature Selection in Fuzzy Decision Systems
  438. Distillation of Large Language Models via Concrete Score Matching
  439. Supporting Creative Ownership through Deep Learning-Based Music Variation
  440. MIDAS: Misalignment-based Data Augmentation Strategy for Imbalanced Multimodal Learning
  441. Kairos: Toward Adaptive and Parameter-Efficient Time Series Foundation Models
  442. Decentralized Asynchronous Multi-player Bandits
  443. Personalized Scientific Figure Caption Generation: An Empirical Study on Author-Specific Writing Style Transfer
  444. Overview of GeoLifeCLEF 2023: Species Composition Prediction with High Spatial Resolution at Continental Scale Using Remote Sensing
  445. RoBiologyDataChoiceQA: A Romanian Dataset for improving Biology understanding of Large Language Models
  446. Adapting SAM with Dynamic Similarity Graphs for Few-Shot Parameter-Efficient Small Dense Object Detection: A Case Study of Chickpea Pods in Field Conditions
  447. CardioForest: An Explainable Ensemble Learning Model for Automatic Wide QRS Complex Tachycardia Diagnosis from ECG
  448. Better with Less: Small Proprietary Models Surpass Large Language Models in Financial Transaction Understanding
  449. Graph Distribution-valued Signals: A Wasserstein Space Perspective
  450. Characterization and Learning of Causal Graphs with Latent Confounders and Post-treatment Selection from Interventional Data
  451. Assessing Algorithmic Bias in Language-Based Depression Detection: A Comparison of DNN and LLM Approaches
  452. EchoingECG: An Electrocardiogram Cross-Modal Model for Echocardiogram Tasks
  453. From Cheap Geometry to Expensive Physics: Elevating Neural Operators via Latent Shape Pretraining
  454. Sharpness of Minima in Deep Matrix Factorization
  455. Deontic Argumentation
  456. A Hamiltonian driven Geometric Construction of Neural Networks via the Lognormal family, Application to Financial Fraud Detection and to Network Security
  457. Online Decision Making with Generative Action Sets
  458. Autonomy-Aware Clustering: When Local Decisions Supersede Global Prescriptions
  459. PCPO: Proportionate Credit Policy Optimization for Aligning Image Generation Models
  460. v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound
  461. Galton's Law of Mediocrity: Why Large Language Models Regress to the Mean and Fail at Creativity in Advertising
  462. TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning
  463. Detecting Hope Across Languages: Multiclass Classification for Positive Online Discourse
  464. Dolphin v1.0 Technical Report
  465. Image-Plane Geometric Decoding for View-Invariant Indoor Scene Reconstruction
  466. Less is More: Towards Simple Graph Contrastive Learning
  467. Test time training enhances in-context learning of nonlinear functions
  468. Dragging with Geometry: From Pixels to Geometry-Guided Image Editing
  469. LieHMR: Autoregressive Human Mesh Recovery with SO(3) Diffusion
  470. The 1st Solution for MOSEv1 Challenge on LSVOS 2025: CGFSeg
  471. A Physics-Guided Probabilistic Surrogate Modeling Framework for Digital Twins of Underwater Radiated Noise
  472. Controlled Generation for Private Synthetic Text
  473. Towards A Transferable Acceleration Method for Density Functional Theory
  474. SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition
  475. Transformer-Based Rate Prediction for Multi-Band Cellular Handsets
  476. The AI Productivity Index (APEX)
  477. Beyond Point Estimates: Likelihood-Based Full-Posterior Wireless Localization
  478. DeepCodeSeek: Real-Time API Retrieval for Context-Aware Code Generation
  479. MuPlon: Multi-Path Causal Optimization for Claim Verification through Controlling Confounding
  480. ProbMed: A Probabilistic Framework for Medical Multimodal Binding
  481. Adaptive Graph Coarsening for Efficient GNN Training
  482. Physics-Informed Learning for Human Whole-Body Kinematics Prediction via Sparse IMUs
  483. Can VLM Pseudo-Labels Train a Time-Series QA Model That Outperforms the VLM?
  484. HNote: Extending YNote with Hexadecimal Encoding for Fine-Tuning LLMs in Music Modeling
  485. CPATTA: Conformal Supervision Allocation For Active Test-Time Adaptation
  486. A Unified Probabilistic Framework for Dictionary Learning with Parsimonious Activation
  487. Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples
  488. The Flaw of Averages: Measuring Benchmark-Level Distributional Robustness
  489. EEG-based AI-BCI Wheelchair Advancement: Transformer-Based Learning with Motor Imagery for Brain Computer Interface
  490. Gradual Capacity Growth for Sparse Network Discovery
  491. QFrBLiMP: a Quebec-French Benchmark of Linguistic Minimal Pairs
  492. On Explaining Proxy Discrimination and Unfairness in Individual Decisions Made by AI Systems
  493. Deep Reinforcement Learning-Based Precoding for Multi-RIS-Aided Multiuser Downlink Systems with Practical Phase Shift
  494. Capacity-Net-Based RIS Precoding Design without Channel Estimation for mmWave MIMO System
  495. YOLO-Based Defect Detection for Metal Sheets
  496. Landmark-Guided Knowledge for Vision-and-Language Navigation
  497. Iterative Residual Cross-Attention Mechanism: An Integrated Approach for Audio-Visual Navigation Tasks
  498. AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentation
  499. The Media Bias Detector: A Framework for Annotating and Analyzing the News at Scale
  500. BaB-prob: Branch and Bound with Preactivation Splitting for Probabilistic Verification of Neural Networks
  501. Deep set based operator learning with uncertainty quantification
  502. Using Images from a Video Game to Improve the Detection of Truck Axles
  503. SOCK: A Benchmark for Measuring Self-Replication in Large Language Models
  504. Generalized Contrastive Learning for Universal Multimodal Retrieval
  505. How Does Preconditioning Guide Feature Learning in Deep Neural Networks?
  506. When Langevin Monte Carlo Meets Randomization: New Sampling Algorithms with Non-asymptotic Error Bounds beyond Log-Concavity and Gradient Lipschitzness
  507. Anchor-free Cross-view Object Geo-localization with Gaussian Position Encoding and Cross-view Association
  508. Layer-wise dynamic rank for compressing large language models
  509. Quadratic Programming Approach for Nash Equilibrium Computation in Multiplayer Imperfect-Information Games
  510. Unsupervised Detection of Spatiotemporal Anomalies in PMU Data Using Transformer-Based BiGAN
  511. Transformers through the lens of support-preserving maps between measures
  512. Effective Model Pruning: Measure The Redundancy of Model Components